mlsanityData to 14 Oct 2026

Rethinking Low-Light Image Enhancement: A Log-Domain Intensity--Chromaticity Decoupling Perspective

arXiv 2605.02627 ↗First posted 4 May 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Explicit reconstruction constraints derived from the decoupled representation are further imposed to suppress abnormal channel amplification and chromatic noise. Experiments on LOLv2-Real, MIT-Adobe FiveK, and LSRW show that the proposed method achieves competitive or superior quantitative and visual performance, reaching 29.71 dB PSNR and 0.89 SSIM on LOLv2-Real. DarkFace experiments further indicate improved downstream face detection under low-light conditions. Code and pretrained models are available at: https://github.com/mubaisam/ICD.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 42 references that are in the map. First posted on arXiv 4 May 2026.

Builds on

19 of 42 references.

References · 19

  1. 2018Deep Retinex Decomposition for Low-Light Enhancementcited by 723
  2. 2020Zero-Reference Deep Curve Estimation for Low-Light Image Enhancementcited by 542
  3. 2019EnlightenGAN: Deep Light Enhancement without Paired Supervisioncited by 466
  4. 2018Learning to See in the Darkcited by 460
  5. 2019Kindling the Darkness: A Practical Low-light Image Enhancercited by 355
  6. 2020Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancementcited by 303
  7. 2021Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimationcited by 192
  8. 2022Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Methodcited by 174
  9. 2023Diff-Retinex: Rethinking Low-light Image Enhancement with A Generative Diffusion Modelcited by 118
  10. 2023Iterative Prompt Learning for Unsupervised Backlit Image Enhancementcited by 107
  11. 2021R2RNet: Low-light Image Enhancement via Real-low to Real-normal Networkcited by 106
  12. 2022LEDNet: Joint Low-light Enhancement and Deblurring in the Darkcited by 96
7 more
  1. 2019UG2+ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environmentscited by 84
  2. 2022You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correctioncited by 81
  3. 2024LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Modelscited by 71
  4. 2021Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancementcited by 60
  5. 2021Semantically Contrastive Learning for Low-light Image Enhancementcited by 31
  6. 2024Fast Context-Based Low-Light Image Enhancement via Neural Implicit Representationscited by 21
  7. 2022Noise Self-Regression: A New Learning Paradigm to Enhance Low-Light Images Without Task-Related Datacited by 12

Built on by

Not cited yet.